import re
from .common import InfoExtractor
-from ..compat import (
- compat_urllib_request,
- compat_urllib_parse,
-)
+from ..compat import compat_urllib_parse_unquote
from ..utils import (
parse_duration,
+ sanitized_Request,
str_to_int,
)
class XTubeIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&#]+))'
+ _VALID_URL = r'(?:xtube:|https?://(?:www\.)?xtube\.com/watch\.php\?.*\bv=)(?P<id>[^/?&#]+)'
_TEST = {
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
'id': 'kVTUy_G222_',
'ext': 'mp4',
'title': 'strange erotica',
- 'description': 'http://www.xtube.com an ET kind of thing',
+ 'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers',
'duration': 450,
'age_limit': 18,
def _real_extract(self, url):
video_id = self._match_id(url)
- req = compat_urllib_request.Request(url)
+ req = sanitized_Request('http://www.xtube.com/watch.php?v=%s' % video_id)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
r'<p class="title">([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
[r"var\s+contentOwnerId\s*=\s*'([^']+)",
- r'By:\s*<a href="/community/profile\.php?user=([^"]+)'],
+ r'By:\s*<a href="/community/profile\.php\?user=([^"]+)'],
webpage, 'uploader', fatal=False)
video_description = self._html_search_regex(
r'<p class="fieldsDesc">([^<]+)',
for format_id, video_url in re.findall(
r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage):
fmt = {
- 'url': compat_urllib_parse.unquote(video_url),
+ 'url': compat_urllib_parse_unquote(video_url),
'format_id': format_id,
}
m = re.search(r'^(?P<height>\d+)[pP]', format_id)
formats.append(fmt)
if not formats:
- video_url = compat_urllib_parse.unquote(self._search_regex(
+ video_url = compat_urllib_parse_unquote(self._search_regex(
r'flashvars\.video_url\s*=\s*"([^"]+)"',
webpage, 'video URL'))
formats.append({'url': video_url})
'url': 'http://www.xtube.com/community/profile.php?user=greenshowers',
'info_dict': {
'id': 'greenshowers',
+ 'age_limit': 18,
},
'playlist_mincount': 155,
}
return {
'_type': 'playlist',
'id': username,
+ 'age_limit': 18,
'entries': [{
'_type': 'url',
'url': eurl,